arrow
返回

Peak response regularization for localization

delete2024-06-28
delete0
delete
OA
AI
J
Jiawei Yu
J
Jinzhen Yao
C
Chuangxin Zhao
X
Xianhong Zhao
Q
Qintao Hu *
DOI:10.1038/s41598-024-65770-2delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Deep convolutional neural networks approaches often assume that the feature response has a Gaussian distribution with target-centered peak response, which can be used to guide the target location and classification. Nevertheless, such an assumption is implausible when there is progressive interference from other targets and/or background noise, which produces sub-peaks on the tracking response map and causes model drift. In this paper, we propose a feature response regularization approach for sub-peak response suppression and peak response enforcement and aim to handle progressive interference systematically. Our approach, referred to as Peak Response Regularization (PRR), applies simple-yet-efficient method to aggregate and align discriminative features, which convert local extremal response in discrete feature space to extremal response in continuous space, which enforces the localization and representation capability of convolutional features. Experiments on human pose detection, object detection, object tracking, and image classification demonstrate that PRR improves the performance of image tasks with a negligible computational cost.
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Scientific Reports 封面图
Scientific Reports
IF:
3.9
论文数:
28.2W
被引数:
83.5W

机构

A
aviation industry corporation of china (avic)
学者数:
1.7K
论文数: 1.4K
被引数: 2
C
chinese academy of sciences
学者数:
56.7W
论文数: 45.0W
被引数: 704
引用论文

引用论文

学者 查看更多内容